File manager - Edit - /usr/local/lib/python3.9/dist-packages/pandas/core/_numba/kernels/mean_.py
Back
""" Numba 1D mean kernels that can be shared by * Dataframe / Series * groupby * rolling / expanding Mirrors pandas/_libs/window/aggregation.pyx """ from __future__ import annotations from typing import TYPE_CHECKING import numba import numpy as np from pandas.core._numba.kernels.shared import is_monotonic_increasing from pandas.core._numba.kernels.sum_ import grouped_kahan_sum if TYPE_CHECKING: from pandas._typing import npt @numba.jit(nopython=True, nogil=True, parallel=False) def add_mean( val: float, nobs: int, sum_x: float, neg_ct: int, compensation: float, num_consecutive_same_value: int, prev_value: float, ) -> tuple[int, float, int, float, int, float]: if not np.isnan(val): nobs += 1 y = val - compensation t = sum_x + y compensation = t - sum_x - y sum_x = t if val < 0: neg_ct += 1 if val == prev_value: num_consecutive_same_value += 1 else: num_consecutive_same_value = 1 prev_value = val return nobs, sum_x, neg_ct, compensation, num_consecutive_same_value, prev_value @numba.jit(nopython=True, nogil=True, parallel=False) def remove_mean( val: float, nobs: int, sum_x: float, neg_ct: int, compensation: float ) -> tuple[int, float, int, float]: if not np.isnan(val): nobs -= 1 y = -val - compensation t = sum_x + y compensation = t - sum_x - y sum_x = t if val < 0: neg_ct -= 1 return nobs, sum_x, neg_ct, compensation @numba.jit(nopython=True, nogil=True, parallel=False) def sliding_mean( values: np.ndarray, result_dtype: np.dtype, start: np.ndarray, end: np.ndarray, min_periods: int, ) -> tuple[np.ndarray, list[int]]: N = len(start) nobs = 0 sum_x = 0.0 neg_ct = 0 compensation_add = 0.0 compensation_remove = 0.0 is_monotonic_increasing_bounds = is_monotonic_increasing( start ) and is_monotonic_increasing(end) output = np.empty(N, dtype=result_dtype) for i in range(N): s = start[i] e = end[i] if i == 0 or not is_monotonic_increasing_bounds: prev_value = values[s] num_consecutive_same_value = 0 for j in range(s, e): val = values[j] ( nobs, sum_x, neg_ct, compensation_add, num_consecutive_same_value, prev_value, ) = add_mean( val, nobs, sum_x, neg_ct, compensation_add, num_consecutive_same_value, prev_value, # pyright: ignore[reportGeneralTypeIssues] ) else: for j in range(start[i - 1], s): val = values[j] nobs, sum_x, neg_ct, compensation_remove = remove_mean( val, nobs, sum_x, neg_ct, compensation_remove ) for j in range(end[i - 1], e): val = values[j] ( nobs, sum_x, neg_ct, compensation_add, num_consecutive_same_value, prev_value, ) = add_mean( val, nobs, sum_x, neg_ct, compensation_add, num_consecutive_same_value, prev_value, # pyright: ignore[reportGeneralTypeIssues] ) if nobs >= min_periods and nobs > 0: result = sum_x / nobs if num_consecutive_same_value >= nobs: result = prev_value elif neg_ct == 0 and result < 0: result = 0 elif neg_ct == nobs and result > 0: result = 0 else: result = np.nan output[i] = result if not is_monotonic_increasing_bounds: nobs = 0 sum_x = 0.0 neg_ct = 0 compensation_remove = 0.0 # na_position is empty list since float64 can already hold nans # Do list comprehension, since numba cannot figure out that na_pos is # empty list of ints on its own na_pos = [0 for i in range(0)] return output, na_pos @numba.jit(nopython=True, nogil=True, parallel=False) def grouped_mean( values: np.ndarray, result_dtype: np.dtype, labels: npt.NDArray[np.intp], ngroups: int, min_periods: int, ) -> tuple[np.ndarray, list[int]]: output, nobs_arr, comp_arr, consecutive_counts, prev_vals = grouped_kahan_sum( values, result_dtype, labels, ngroups ) # Post-processing, replace sums that don't satisfy min_periods for lab in range(ngroups): nobs = nobs_arr[lab] num_consecutive_same_value = consecutive_counts[lab] prev_value = prev_vals[lab] sum_x = output[lab] if nobs >= min_periods: if num_consecutive_same_value >= nobs: result = prev_value * nobs else: result = sum_x else: result = np.nan result /= nobs output[lab] = result # na_position is empty list since float64 can already hold nans # Do list comprehension, since numba cannot figure out that na_pos is # empty list of ints on its own na_pos = [0 for i in range(0)] return output, na_pos
| ver. 1.4 |
Github
|
.
| PHP 7.4.33 | Generation time: 0.42 |
proxy
|
phpinfo
|
Settings